Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157818
Manikandan Pounraj, Linu Lonappan, Varangal Shaik Roshan Ali, Adam Louis D'couto, Dakaraju Lakshmi Deepak, Rugmini R Krishnan
Automation is a process of increasing production and reducing the downtime of any industry. With the integration of sensor data to the cloud using an OPC-VA communication protocol, the automation becomes more prominent and interesting. However, many existing industrial controllers do not support open platform communication unified architecture (OPC-VA) and it needs an IIoT device to connect the cloud. The existing programmable logic controller in any industry have to be connected to an IIoT device through Ethernet. Sensors connected to the controller will transmit the data to the IIoT device. The transmission can also be bidirectional. In this paper, a conveyor which distributes packages is simulated in Codesys and it is visualized in a human-machine interface (HMI) screen which is in-built in the software. The hardware set-up is made with the industrial controller to execute the same. A methodology to send the data from the controller to the cloud using open platform communication unified architecture (OPC-UA) is proposed
{"title":"Structured text programming to visualize the distribution of packages on a conveyor","authors":"Manikandan Pounraj, Linu Lonappan, Varangal Shaik Roshan Ali, Adam Louis D'couto, Dakaraju Lakshmi Deepak, Rugmini R Krishnan","doi":"10.1109/ICEEICT56924.2023.10157818","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157818","url":null,"abstract":"Automation is a process of increasing production and reducing the downtime of any industry. With the integration of sensor data to the cloud using an OPC-VA communication protocol, the automation becomes more prominent and interesting. However, many existing industrial controllers do not support open platform communication unified architecture (OPC-VA) and it needs an IIoT device to connect the cloud. The existing programmable logic controller in any industry have to be connected to an IIoT device through Ethernet. Sensors connected to the controller will transmit the data to the IIoT device. The transmission can also be bidirectional. In this paper, a conveyor which distributes packages is simulated in Codesys and it is visualized in a human-machine interface (HMI) screen which is in-built in the software. The hardware set-up is made with the industrial controller to execute the same. A methodology to send the data from the controller to the cloud using open platform communication unified architecture (OPC-UA) is proposed","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128958012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10156921
Latha R, Suhas A R, B. P. Pradeep Kumar, M.Mohammed Ibrahim, Sathiyapriya V
Speech Enhancement (SE) aims to improve the quality of degraded speech while maintaining its intelligibility. The Wavelet Transform (WT) has become a powerful tool of signal analysis thereby widely used in signal detection and signal denoising. In this paper, we propose an effective means of SE by a hybrid threshold scheme using WT. The proposed methodology looks into both falling the noise and preserving edges of the speech signal unlike the conventional Hybrid Threshold (HT) and Soft Threshold (ST) in the wavelet domain. The threshold value in the wavelet domain is maintained constant for all sub-bands of the signal which reduces denoising efficiency. A novel speech augmentation technique built on the wavelet onsets and time adaption of introduced by calculating wavelet coefficients of the Teager Energy. Performance analysis of speech enhancement techniques using Wavelet coefficients and Teager Energy Operator (TEO) with hybrid threshold method is done. The experiment is carried out for speech data with various values of SNR vacillating from -10 to +10 db with Additive White Gaussian Noise (AWGN).
{"title":"Hybrid Threshold Speech Enhancement Scheme Using TEO And Wavelet Coefficients","authors":"Latha R, Suhas A R, B. P. Pradeep Kumar, M.Mohammed Ibrahim, Sathiyapriya V","doi":"10.1109/ICEEICT56924.2023.10156921","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10156921","url":null,"abstract":"Speech Enhancement (SE) aims to improve the quality of degraded speech while maintaining its intelligibility. The Wavelet Transform (WT) has become a powerful tool of signal analysis thereby widely used in signal detection and signal denoising. In this paper, we propose an effective means of SE by a hybrid threshold scheme using WT. The proposed methodology looks into both falling the noise and preserving edges of the speech signal unlike the conventional Hybrid Threshold (HT) and Soft Threshold (ST) in the wavelet domain. The threshold value in the wavelet domain is maintained constant for all sub-bands of the signal which reduces denoising efficiency. A novel speech augmentation technique built on the wavelet onsets and time adaption of introduced by calculating wavelet coefficients of the Teager Energy. Performance analysis of speech enhancement techniques using Wavelet coefficients and Teager Energy Operator (TEO) with hybrid threshold method is done. The experiment is carried out for speech data with various values of SNR vacillating from -10 to +10 db with Additive White Gaussian Noise (AWGN).","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127602032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157395
K. K, Vijayakumar N C, Poovizhi P, D. Selvapandian
Precipitation expectation is hugely critical in day-to-day existence standard just as for water asset the board, stochastic hydrology, and rain run-off displaying and flood hazard relief. Machine Learning (ML) strategies can operate computational techniques and anticipate precipitation by extracting and integrating the obscured information from the linear and non-linear trends of previous atmosphere information. Different devices and strategies for estimating precipitation are at present reachable; however, there is as yet a paucity of precise outcomes. Earlier techniques are impending short at whatever point monstrous datasets are utilized for precipitation estimate. In this research, a few models and strategies were applied to anticipate the precipitation information Nellore Station, AP State, India. The relative review was led zeroing in on creating and contrasting a few ML models, assessing various situations and time skyline, and gauging precipitation utilizing two kinds of techniques. The anticipation approach uses four distinct ML calculations, which are Bayesian-Linear-Regression (BLR), Boosted-Decision-Tree-Regression (BDTR), Decision-Forest-Regression (DFR) and Neural-Network-Regression (NNR). Then again, the precipitation was anticipated on various time skyline by utilizing distinctive ML models which is strategy 1 (M1): Predicting Rainfall by Autocorrelation-Function (ACF) and technique 2 (M2): Predicting Rainfall by forecasting Error. The outcomes show that, two distinct strategies have been applied with various situations and diverse time skylines, and M1 displays a preferably high exactness over M2 utilizing BDTR demonstrating.
{"title":"An Efficient Rainfall Forecasting System using Machine Learning Methods","authors":"K. K, Vijayakumar N C, Poovizhi P, D. Selvapandian","doi":"10.1109/ICEEICT56924.2023.10157395","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157395","url":null,"abstract":"Precipitation expectation is hugely critical in day-to-day existence standard just as for water asset the board, stochastic hydrology, and rain run-off displaying and flood hazard relief. Machine Learning (ML) strategies can operate computational techniques and anticipate precipitation by extracting and integrating the obscured information from the linear and non-linear trends of previous atmosphere information. Different devices and strategies for estimating precipitation are at present reachable; however, there is as yet a paucity of precise outcomes. Earlier techniques are impending short at whatever point monstrous datasets are utilized for precipitation estimate. In this research, a few models and strategies were applied to anticipate the precipitation information Nellore Station, AP State, India. The relative review was led zeroing in on creating and contrasting a few ML models, assessing various situations and time skyline, and gauging precipitation utilizing two kinds of techniques. The anticipation approach uses four distinct ML calculations, which are Bayesian-Linear-Regression (BLR), Boosted-Decision-Tree-Regression (BDTR), Decision-Forest-Regression (DFR) and Neural-Network-Regression (NNR). Then again, the precipitation was anticipated on various time skyline by utilizing distinctive ML models which is strategy 1 (M1): Predicting Rainfall by Autocorrelation-Function (ACF) and technique 2 (M2): Predicting Rainfall by forecasting Error. The outcomes show that, two distinct strategies have been applied with various situations and diverse time skylines, and M1 displays a preferably high exactness over M2 utilizing BDTR demonstrating.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121466834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157876
Meniga Venkata Lakshmi Narayana, K. Nagabhushanam, R. Kiranmayi, M. Rathaiah
Photovoltaic (PV) generating devices, which use solar energy, have seen widespread use in modern power grids. Improving the efficiency of the PV system is essential for reaching full potential. Continuously collecting the greatest power from the PV arrays when environmental circumstances change is the key to realising this advantage. To optimise the performance of the PV system as a whole, maximum power point tracking (MPPT) must be implemented. INC, perturb-and-observe, fractional short-circuit current, fractional open-circuit voltage, and hill climbing are some of the most used MPPT techniques. Many different approaches to MPPT for PV system control have emerged in response to developments in artificial intelligence technology. However, the efficiency and resilience of such approaches are low. The primary goal of this work is to increase the efficiency of maximum power point tracking (MPPT) by the use of variable step size incremental conductance. Fuzzy logic-based step size adjustment for incremental conductance (INC) maximum power point tracking (MPPT) for PV. This research calculates voltage step magnitude based on power-voltage relation steepness. A unique treatment that introduces five effective regions around the point of maximal PV production achieves this. A fuzzy logic system adjusts the duty cycle's step size using the fuzzy inputs' placements in the five regions. The current-voltage ratio and its derivatives determine the fuzzy inputs while appropriate membership functions and fuzzy rules are built. The suggested method's advantage is that it allows the MPPT efficiency to be adjusted by changing the size of the incremental conductance step. The main controller used is Fuzzy Logic Controller, but this controller may not achieve the required parameters. Many rules are there, that are needed to be follow while implementing the work. And also, does not adaptable for all the varying parameters in the system. To overcome this problem, a magnified controller known as ANFIS Controller. This ANFIS Controller will replaces the Fuzzy Logic Controller in the controlling topology. This controller works by using both ANN and FLC based rules and characteristics. By using this controller, we can be improving the dynamic response of the system and the tuning of membership functions can be possible to obtain the required output. It also produces stable signals in the system. The transient behaviour of the system can be improved. The performance results of this extension method can be evaluated by using MATLAB/SIMULINK environment.
{"title":"A Novel Variable Step Incremental Conductance Maximum Power Point Tracking Algorithm based on ANFIS Controller for Grid Photovoltaic Systems","authors":"Meniga Venkata Lakshmi Narayana, K. Nagabhushanam, R. Kiranmayi, M. Rathaiah","doi":"10.1109/ICEEICT56924.2023.10157876","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157876","url":null,"abstract":"Photovoltaic (PV) generating devices, which use solar energy, have seen widespread use in modern power grids. Improving the efficiency of the PV system is essential for reaching full potential. Continuously collecting the greatest power from the PV arrays when environmental circumstances change is the key to realising this advantage. To optimise the performance of the PV system as a whole, maximum power point tracking (MPPT) must be implemented. INC, perturb-and-observe, fractional short-circuit current, fractional open-circuit voltage, and hill climbing are some of the most used MPPT techniques. Many different approaches to MPPT for PV system control have emerged in response to developments in artificial intelligence technology. However, the efficiency and resilience of such approaches are low. The primary goal of this work is to increase the efficiency of maximum power point tracking (MPPT) by the use of variable step size incremental conductance. Fuzzy logic-based step size adjustment for incremental conductance (INC) maximum power point tracking (MPPT) for PV. This research calculates voltage step magnitude based on power-voltage relation steepness. A unique treatment that introduces five effective regions around the point of maximal PV production achieves this. A fuzzy logic system adjusts the duty cycle's step size using the fuzzy inputs' placements in the five regions. The current-voltage ratio and its derivatives determine the fuzzy inputs while appropriate membership functions and fuzzy rules are built. The suggested method's advantage is that it allows the MPPT efficiency to be adjusted by changing the size of the incremental conductance step. The main controller used is Fuzzy Logic Controller, but this controller may not achieve the required parameters. Many rules are there, that are needed to be follow while implementing the work. And also, does not adaptable for all the varying parameters in the system. To overcome this problem, a magnified controller known as ANFIS Controller. This ANFIS Controller will replaces the Fuzzy Logic Controller in the controlling topology. This controller works by using both ANN and FLC based rules and characteristics. By using this controller, we can be improving the dynamic response of the system and the tuning of membership functions can be possible to obtain the required output. It also produces stable signals in the system. The transient behaviour of the system can be improved. The performance results of this extension method can be evaluated by using MATLAB/SIMULINK environment.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124509669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157285
M. Suresh, R. Rajan, Joshua Thomas
Dysarthria is a motor speech disorder that results in speech difficulties due to the weakness of associated muscles. This unclear speech makes it difficult for dysarthric patients to present himself understood. This neurological limitation is usually occurs due to damages to the brain or central nervous system. Speech therapy can be effectively employed to enhance the range and consistency of voice production and improve intelligibility and communicative effectiveness. Assessing the degree of severity of dysarthria provides vital information on the patient's progress which inturn assists pathologists in arriving at a treatment plan that includes developing automated voice recognition system suitable for dysarthria patients. This work performs an exhaustive study on dysarthria severity level classification using deep neural network (DNN) and convolution neural network (CNN) architectures. Mel Frequency Cepstral Coefficients (MFCCs) and their derivatives constitute feature vectors for classification. Using the UA-Speech database, the performance metrics of DNN/CNN based learning models have been compared to baseline classifiers like support vector machine (SVM) and Random Forest (RF). The highest classification accuracy of 97.6% is reported for DNN under UA speech database. A detailed examination of the performance from the models discussed above reveal that appropriate choice of deep learning architecture ensures better results than traditional classifiers like SVM and Random Forest.
{"title":"Dysarthria Speech Disorder Classification Using Traditional and Deep Learning Models","authors":"M. Suresh, R. Rajan, Joshua Thomas","doi":"10.1109/ICEEICT56924.2023.10157285","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157285","url":null,"abstract":"Dysarthria is a motor speech disorder that results in speech difficulties due to the weakness of associated muscles. This unclear speech makes it difficult for dysarthric patients to present himself understood. This neurological limitation is usually occurs due to damages to the brain or central nervous system. Speech therapy can be effectively employed to enhance the range and consistency of voice production and improve intelligibility and communicative effectiveness. Assessing the degree of severity of dysarthria provides vital information on the patient's progress which inturn assists pathologists in arriving at a treatment plan that includes developing automated voice recognition system suitable for dysarthria patients. This work performs an exhaustive study on dysarthria severity level classification using deep neural network (DNN) and convolution neural network (CNN) architectures. Mel Frequency Cepstral Coefficients (MFCCs) and their derivatives constitute feature vectors for classification. Using the UA-Speech database, the performance metrics of DNN/CNN based learning models have been compared to baseline classifiers like support vector machine (SVM) and Random Forest (RF). The highest classification accuracy of 97.6% is reported for DNN under UA speech database. A detailed examination of the performance from the models discussed above reveal that appropriate choice of deep learning architecture ensures better results than traditional classifiers like SVM and Random Forest.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115268053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157007
P. Asha, K. Nagabhushanam, R. Kiranmayi, M. Rathaiah
In this paper an Fuzzy Inference System based battery pack charge and discharge control is achieved in renewable micro grid application. The charge and discharge of the battery pack is determined by the load demand, State of charge of the battery and available power from the micro grid sources. The micro grid comprises of solar plant, fuel cell, wind farm, biomass plant, diesel generator and Battery Energy Storage System. The proposed control module has the capability to avoid overcharge and overdischarge as per the powers from the sources. The Fuzzy Inference System is later updated with Adaptive Neuro Fuzzy Inference System module for better estimation of the battery current improving the micro grid performance. Adaptive Neuro Fuzzy Inference System is less complex module which has simple linear rule base trained by optimization technique controlling the battery current. The micro grid is operated in different operating conditions with change in power generation and load demand. The modeling is designed in MATLAB Simulink environment with graphs generated taking time as reference. A comparative analysis is carried out with FIS and ANFIS modules in the test system with comparative graphs.
{"title":"Multiple Renewable Sources Integrated Micro Grid with ANFIS Based Charge and Discharge Control of Battery for Optimal Power Sharing","authors":"P. Asha, K. Nagabhushanam, R. Kiranmayi, M. Rathaiah","doi":"10.1109/ICEEICT56924.2023.10157007","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157007","url":null,"abstract":"In this paper an Fuzzy Inference System based battery pack charge and discharge control is achieved in renewable micro grid application. The charge and discharge of the battery pack is determined by the load demand, State of charge of the battery and available power from the micro grid sources. The micro grid comprises of solar plant, fuel cell, wind farm, biomass plant, diesel generator and Battery Energy Storage System. The proposed control module has the capability to avoid overcharge and overdischarge as per the powers from the sources. The Fuzzy Inference System is later updated with Adaptive Neuro Fuzzy Inference System module for better estimation of the battery current improving the micro grid performance. Adaptive Neuro Fuzzy Inference System is less complex module which has simple linear rule base trained by optimization technique controlling the battery current. The micro grid is operated in different operating conditions with change in power generation and load demand. The modeling is designed in MATLAB Simulink environment with graphs generated taking time as reference. A comparative analysis is carried out with FIS and ANFIS modules in the test system with comparative graphs.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114171494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157672
Hari Kishan Neelakantam, Bindu Priya Makala, Prasanna Kommoju, Devi Sai Revanth Ogirala, Pacharla Naga Suneel, Manoj Kumar D
With the growing demand for wireless communication, there is an increasing need for efficient and reliable sharing of unlicensed frequency bands. Due to the difficulties involved in sharing the same frequency spectrum, the coexistence between LTE and WLAN over unlicensed bands has emerged as a significant area of research. This paper presents a study on the LTE co-existence with WLAN in unlicensed spectrum using NS-3. Our paper comes up with a hybrid network analyzer that implements Maximum throughput scheduling and exponential rule algorithm along with cat4 LAA LBT for achieving fair co-existence. The performance of these mechanisms is evaluated in terms of throughput, latency and fairness. The study also includes an investigation of the impact of various network parameters such as network topology, traffic load, and interference. The outcomes demonstrate that the suggested hybrid network analyzer can effectively manage the LTE, and WLAN co- existence in unlicensed bands, providing high throughput and fair resource allocation.
{"title":"LTE and WLAN fair co-existence in unlicensed bands","authors":"Hari Kishan Neelakantam, Bindu Priya Makala, Prasanna Kommoju, Devi Sai Revanth Ogirala, Pacharla Naga Suneel, Manoj Kumar D","doi":"10.1109/ICEEICT56924.2023.10157672","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157672","url":null,"abstract":"With the growing demand for wireless communication, there is an increasing need for efficient and reliable sharing of unlicensed frequency bands. Due to the difficulties involved in sharing the same frequency spectrum, the coexistence between LTE and WLAN over unlicensed bands has emerged as a significant area of research. This paper presents a study on the LTE co-existence with WLAN in unlicensed spectrum using NS-3. Our paper comes up with a hybrid network analyzer that implements Maximum throughput scheduling and exponential rule algorithm along with cat4 LAA LBT for achieving fair co-existence. The performance of these mechanisms is evaluated in terms of throughput, latency and fairness. The study also includes an investigation of the impact of various network parameters such as network topology, traffic load, and interference. The outcomes demonstrate that the suggested hybrid network analyzer can effectively manage the LTE, and WLAN co- existence in unlicensed bands, providing high throughput and fair resource allocation.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115831447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157750
I. K. Pradeep, K. B. Kiran, B.CH.S.N.L.S. Sai Baba, G. K. M. Devarakonda, M. D. Satish
Sentiment analysis is the area of research for analyzing customer opinions on services or products delivered by an entity. With the evaluation of deep learning, the recurrent neural network is picked as the preferred method for most of the sentiment analysis research. The goal of this paper is to build a model that uses minimum parameters without compromising too much on the performance. Three models are built on the publicly available dataset. The performance of these models is then evaluated. It is observed that the model using long-short term memory gives very good performance among all the models but uses too many parameters. The last model uses average of word embeddings which uses half of the parameters used in the previous model and its performance is very much near to the previous one.
{"title":"Efficient Sentiment classification with Minimal parameters using Average Embedding Approach","authors":"I. K. Pradeep, K. B. Kiran, B.CH.S.N.L.S. Sai Baba, G. K. M. Devarakonda, M. D. Satish","doi":"10.1109/ICEEICT56924.2023.10157750","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157750","url":null,"abstract":"Sentiment analysis is the area of research for analyzing customer opinions on services or products delivered by an entity. With the evaluation of deep learning, the recurrent neural network is picked as the preferred method for most of the sentiment analysis research. The goal of this paper is to build a model that uses minimum parameters without compromising too much on the performance. Three models are built on the publicly available dataset. The performance of these models is then evaluated. It is observed that the model using long-short term memory gives very good performance among all the models but uses too many parameters. The last model uses average of word embeddings which uses half of the parameters used in the previous model and its performance is very much near to the previous one.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115441395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157441
M. S. Muthukkumar, S. Diwakaran, C. M. A. Kumar
The presented methodology is an energy-optimized data routing mechanism for wireless sensor networks (WSNs) that emphasizes energy conservation while providing reliable data delivery to the base station (BS). Hierarchical and cluster-based protocol consists of one cluster head (CH) node, two deputy CH nodes, and extra sensor nodes per cluster. The introduction of the concept of a CH panel reduces the time and energy required for re-clustering. The BS selects a group of likely CH nodes and constructs the CH panel with the objective of attaining a defined BS throughput level. The transfer of data between CH nodes and the BS might occur directly or via multi-hop pathways. During periods of data congestion, alternative channels are sometimes employed to increase the network dependability of data transmission. Simulation findings suggest that the proposed protocol improves the energy efficiency, data throughput, and lifetime of a cluster's nodes.
{"title":"Self Asserted Power Optimization Protocol for Heterogeneous WSN","authors":"M. S. Muthukkumar, S. Diwakaran, C. M. A. Kumar","doi":"10.1109/ICEEICT56924.2023.10157441","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157441","url":null,"abstract":"The presented methodology is an energy-optimized data routing mechanism for wireless sensor networks (WSNs) that emphasizes energy conservation while providing reliable data delivery to the base station (BS). Hierarchical and cluster-based protocol consists of one cluster head (CH) node, two deputy CH nodes, and extra sensor nodes per cluster. The introduction of the concept of a CH panel reduces the time and energy required for re-clustering. The BS selects a group of likely CH nodes and constructs the CH panel with the objective of attaining a defined BS throughput level. The transfer of data between CH nodes and the BS might occur directly or via multi-hop pathways. During periods of data congestion, alternative channels are sometimes employed to increase the network dependability of data transmission. Simulation findings suggest that the proposed protocol improves the energy efficiency, data throughput, and lifetime of a cluster's nodes.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115474379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157004
Muneeb Wali, Ashish Sharma
The majority of the recent trends in photovoltaic (PV) energy utilization can be attributed to major global legislation intended to reduce the use of fossil fuels. However, the performance of these solar PV system gets affects by various faults that must be identified. In this regard, an effective and highly accurate solar PV fault detection method is proposed wherein Artificial Neural network (ANN) and Honey Badger Algorithm (HBA) have been used. The main motive of proposed HBA-ANN model is to enhance the accuracy of PV fault detection while lowering the complexity of model. We used a PV fault dataset from GitHub, which was later balanced and impartial, to achieve this goal. Also, during the pre-processing stage, the input and target variables are isolated. The next stage, in which the ANN is initialized and weights are determined. An HBA optimization procedure is then used to optimize or tune the value of these weights. Furthermore, by contrasting the suggested HBA-ANN model's performance with that of more established models like the Tree, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Artificial Neural Network, the model's effectiveness is evaluated and validated. The simulated results were obtained for both phases, i.e. the training phase as well as the testing phase in terms of accuracy, precision, recall, and Fscore. The results of the simulations showed that the suggested HBA-ANN model outperformed all other comparable models in terms of every factor, demonstrating its superiority.
{"title":"An Online Fault Detection and Classification Monitoring scheme for Photovoltaic Plants","authors":"Muneeb Wali, Ashish Sharma","doi":"10.1109/ICEEICT56924.2023.10157004","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157004","url":null,"abstract":"The majority of the recent trends in photovoltaic (PV) energy utilization can be attributed to major global legislation intended to reduce the use of fossil fuels. However, the performance of these solar PV system gets affects by various faults that must be identified. In this regard, an effective and highly accurate solar PV fault detection method is proposed wherein Artificial Neural network (ANN) and Honey Badger Algorithm (HBA) have been used. The main motive of proposed HBA-ANN model is to enhance the accuracy of PV fault detection while lowering the complexity of model. We used a PV fault dataset from GitHub, which was later balanced and impartial, to achieve this goal. Also, during the pre-processing stage, the input and target variables are isolated. The next stage, in which the ANN is initialized and weights are determined. An HBA optimization procedure is then used to optimize or tune the value of these weights. Furthermore, by contrasting the suggested HBA-ANN model's performance with that of more established models like the Tree, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Artificial Neural Network, the model's effectiveness is evaluated and validated. The simulated results were obtained for both phases, i.e. the training phase as well as the testing phase in terms of accuracy, precision, recall, and Fscore. The results of the simulations showed that the suggested HBA-ANN model outperformed all other comparable models in terms of every factor, demonstrating its superiority.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115847468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：